[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1338830279.28282.117.camel@twins>
Date: Mon, 04 Jun 2012 19:17:59 +0200
From: Peter Zijlstra <a.p.zijlstra@...llo.nl>
To: Vladimir Davydov <VDavydov@...allels.com>
Cc: Arjan van de Ven <arjan@...ux.intel.com>,
Ingo Molnar <mingo@...e.hu>, Len Brown <lenb@...nel.org>,
Andrew Morton <akpm@...ux-foundation.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] cpuidle: menu: use nr_running instead of cpuload for
calculating perf mult
On Mon, 2012-06-04 at 21:08 +0400, Vladimir Davydov wrote:
> But this_cpu_load(), which is currently used by cpuidle, does not
> return the "load average". It returns the value of cpuload at some
> moment in the past (actually, the value is updated in
> update_cpu_load()). This value is usually used for load balancing.
>
> Moreover, this value does not reflect the real cpu load from the
> cpuidle pow, because it depends on tasks priority (nice) and, what is
> worse, with the introduction of cgroups it can be pretty arbitrary.
> For instance, each group of tasks is accounted just as a single task
> with standard priority "spreaded" among all cpus, no matter how many
> tasks are actually running in it.
Indeed.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists